Neural Programmer-Interpreters
Abstract
We propose the neural programmer-interpreter (NPI): a recurrent and compositional neural network that learns to represent and execute programs. NPI has three learnable components: a task-agnostic recurrent core, a persistent key-value program memory, and domain-specific encoders that enable a single NPI to operate in multiple perceptually diverse environments with distinct affordances. By learning to compose lower-level programs to express higher-level programs, NPI reduces sample complexity and increases generalization ability compared to sequence-to-sequence LSTMs. The program memory allows efficient learning of additional tasks by building on existing programs. NPI can also harness the environment (e.g. a scratch pad with read-write pointers) to cache intermediate results of computation, lessening the long-term memory burden on recurrent hidden units. In this work we train the NPI with fully-supervised execution traces; each program has example sequences of calls to the immediate subprograms conditioned on the input. Rather than training on a huge number of relatively weak labels, NPI learns from a small number of rich examples. We demonstrate the capability of our model to learn several types of compositional programs: addition, sorting, and canonicalizing 3D models. Furthermore, a single NPI learns to execute these programs and all 21 associated subprograms.
Cite
Text
Reed and de Freitas. "Neural Programmer-Interpreters." International Conference on Learning Representations, 2016.Markdown
[Reed and de Freitas. "Neural Programmer-Interpreters." International Conference on Learning Representations, 2016.](https://mlanthology.org/iclr/2016/reed2016iclr-neural/)BibTeX
@inproceedings{reed2016iclr-neural,
title = {{Neural Programmer-Interpreters}},
author = {Reed, Scott E. and de Freitas, Nando},
booktitle = {International Conference on Learning Representations},
year = {2016},
url = {https://mlanthology.org/iclr/2016/reed2016iclr-neural/}
}